Stable Diffusion 3.5: Medium, Large and Turbo Models for ComfyUI

Stability AI's SD 3.5 open image models: Medium, Large, Turbo, and related ControlNets.

S

Stable Diffusion 3.5

Text-to-ImageOpen SourceMMDiT

Stability AI open image models with MMDiT architecture — strong text rendering and multi-subject composition. Use Stability AI checkpoints for FP16; Comfy-Org for FP8 all-in-one / scaled packs.

SD3.5 LargeComfy-Org FP8GitHubAnnouncementPaper (SD3)
DeveloperStability AI
ArchitectureMMDiT — CLIP-L / CLIP-G / T5-XXL text encoders
LicenseStability AI Community License
Native resolution1024×1024 (multi-aspect supported)
VariantsMedium (2.5B), Large (8B), Large Turbo (4-step), Comfy-Org FP8
ComfyUI guide/en/tutorial/advanced/stable-diffusion-3-5-comfyui-workflow

Guides and workflows related to this model series.

Stable Diffusion 3.5 Workflow Tutorial in ComfyUI
Stable Diffusion 3.5 Workflow Tutorial in ComfyUI

This article introduces the Stable Diffusion 3.5 Workflow Tutorial in ComfyUI.

SD3.5